Microsoft Certified: Azure AI Engineer AssociateImplement knowledge mining solutionsMedium
A company is building a knowledge mining solution that processes a large volume of unstructured text documents. They need to extract specific pieces of information, such as product names, customer names, and order numbers, which are not always in a fixed format or location within the documents. Which Azure AI Language feature is most suitable for identifying and extracting these types of entities?
- ALanguage Detection
- BNamed Entity Recognition (NER)
- CKey Phrase Extraction
- DSentiment Analysis
Show answer & explanationAnswer & explanation
Correct answer: B. Named Entity Recognition (NER)
Named Entity Recognition (NER) is specifically designed to identify and categorize named entities (like people, organizations, locations, product names, etc.) from unstructured text, regardless of their position or formatting, making it ideal for extracting specific information like product names and order numbers.
Why the other options are wrong
- A. Language Detection identifies the language of the text, not entities within it.
- C. Key Phrase Extraction identifies general concepts or topics, not specific named entities like product or customer names.
- D. Sentiment Analysis determines the emotional tone of text, not specific entities.
Named Entity Recognition (NER)
An Azure AI Language feature that identifies and categorizes specific entities within text, such as people, places, organizations, dates, and product names.
- Extracts structured information from unstructured text.
- Helps in information retrieval and knowledge graph creation.
- Supports various entity categories.
Memory trick: To 'name' the important things in a document, you need 'Named Entity Recognition' to spot them.